Lab S7 - AI assisted analysis of the NEON MAG taxonomy, soil chemistry and location data - Part II

library(tidyverse)
library(lubridate)
library(DT)
library(viridis)
library(janitor)
library(plotly)
library(respirometry)

2. Load the dataset

# Ensure NEON_soilMAGs_soilChem.csv is in your working directory
data <- read_csv("NEON_soilMAGs_soilChem.csv") %>% clean_names()

4. Visualization: Phylum Relative Abundance vs. Soil pH

# 1. Update the env_analysis to use the correct pH column name
env_analysis <- data %>%
  filter(!is.na(soil_in_waterp_h), !is.na(soil_moisture)) %>%
  group_by(site_id, soil_in_waterp_h, soil_moisture, phylum) %>%
  summarise(count = n(), .groups = 'drop') %>%
  group_by(site_id) %>%
  mutate(relative_abundance = count / sum(count))

# 2. Re-create the plot using the correct x-axis variable
plot_ph <- ggplot(env_analysis, aes(x = soil_in_waterp_h, y = relative_abundance, color = phylum)) +
  geom_point(alpha = 0.6) +
  geom_smooth(method = "lm", se = FALSE) +
  scale_color_viridis_d() +
  theme_minimal() +
  labs(title = "Microbial Phylum Abundance vs. Soil pH",
       x = "Soil pH (Water)",
       y = "Relative Abundance",
       color = "Phylum")

plot_ph

ggplotly(plot_ph)

5. Visualization: Phylum Relative Abundance vs. Soil Moisture

plot_moisture <- ggplot(env_analysis, aes(x = soil_moisture, y = relative_abundance, color = phylum)) +
  geom_point(alpha = 0.6) +
  geom_smooth(method = "lm", se = FALSE) +
  scale_color_viridis_d() +
  theme_minimal() +
  labs(title = "Microbial Phylum Abundance vs. Soil Moisture",
       x = "Soil Moisture content",
       y = "Relative Abundance",
       color = "Phylum")

ggplotly(plot_moisture)

7. Summary Table for Lab Report

summary_table <- env_analysis %>%
  group_by(phylum) %>%
  summarise(avg_abundance = mean(relative_abundance),
            max_abundance = max(relative_abundance)) %>%
  arrange(desc(avg_abundance))

datatable(summary_table, caption = "Summary of Phylum Abundance Across Sites")